youtube-dl/youtube_dl/extractor/tf1.py

52 lines
2.1 KiB
Python
Raw Normal View History

2013-06-29 06:18:19 -07:00
# coding: utf-8
2014-03-29 07:05:15 -07:00
from __future__ import unicode_literals
2013-06-29 06:18:19 -07:00
from .common import InfoExtractor
2014-03-29 07:05:15 -07:00
2013-06-29 06:18:19 -07:00
class TF1IE(InfoExtractor):
"""TF1 uses the wat.tv player."""
2015-05-30 03:18:11 -07:00
_VALID_URL = r'http://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html'
2015-05-25 22:32:43 -07:00
_TESTS = [{
2014-03-29 07:05:15 -07:00
'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
'info_dict': {
'id': '10635995',
'ext': 'mp4',
'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle',
'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
},
'params': {
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
},
2015-01-03 16:05:31 -08:00
}, {
'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
'info_dict': {
2015-01-03 16:43:55 -08:00
'id': '12043945',
2015-01-03 16:05:31 -08:00
'ext': 'mp4',
'title': 'Le grand Mystérioso - Chuggington',
2015-01-03 16:43:55 -08:00
'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.',
'upload_date': '20150103',
2015-01-03 16:05:31 -08:00
},
'params': {
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
},
2015-05-25 22:32:43 -07:00
}, {
'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
'only_matching': True,
2015-05-30 03:18:11 -07:00
}, {
'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html',
'only_matching': True,
2015-05-25 22:32:43 -07:00
}]
2013-06-29 06:18:19 -07:00
def _real_extract(self, url):
2015-01-03 16:05:31 -08:00
video_id = self._match_id(url)
2014-03-29 07:05:15 -07:00
webpage = self._download_webpage(url, video_id)
2015-12-15 07:09:14 -08:00
wat_id = self._html_search_regex(
2015-12-15 07:11:52 -08:00
r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
2015-12-15 07:09:14 -08:00
webpage, 'wat id', group='id')
2014-03-29 07:05:15 -07:00
wat_info = self._download_json(
'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id)
return self.url_result(wat_info['media']['url'], 'Wat')